The explosive growth of data has led to a profound revolution in data science, particularly in the field of image processing. Graph techniques provide flexibility and efficiency in capturing geometric structures of the imaging data. Major challenges in graph-related problems include graph representation of high-dimensional data, regularization on graphs, and fast algorithms. This mini-symposium aims to showcase a broad spectrum of topics in graph techniques for image processing. The presentations will focus on theoretical aspects of graph representation, computational advances, as well as applications in imaging sciences.

Graph Regularized EEG Source Imaging with In-Class Consistency and Out-Class Discrimination

Yifei Lou (University of Texas at Dallas)

A Graph Framework for Manifold-Valued Data

Daniel Tenbrinck (University of Münster)

An Auction Dynamics Approach to Data Classification

Ekaterina Rapinchuk (Michigan State University)

Cut Pursuit: A Working Set Strategy to Find Piecewise Constant Functions on Graphs

Loic Landrieu (Institut géographique national)

EEG Source Imaging based on Spatial and Temporal Graph Structures

Jing Qin (Montana State University)

Interpolation on High Dimensional Point Cloud

Zuoqiang Shi (Tsinghua University)

On the Front Propagation on Weighted Graphs With Applications in Image Processing and High-Dimensional Data

Abderrahim Elmoataz (University of Caen Normandie, CNRS)

Organizers:

Yifei Lou (University of Texas at Dallas)

Jing Qin (Montana State University)

Keywords:

image reconstruction, image representation, image segmentation, inverse problems, nonlinear optimization